前言
最近工作上遇到一个问题,后端有一个定时任务,需要用JAVA每天判断法定节假日、周末放假,上班等情况,
其实想单独通过逻辑什么的去判断中国法定节假日的放假情况,基本不可能,因为国家每一年的假期可能不一样,是人为设定的;
所以只能依靠其它手段,能想到的比较靠谱的如下:
- 网络接口:有些数据服务商会提供,要么是收钱的,要么是次数限制,等等各种问题,效果不理想,可控性差,我也没试过,如:https://www.juhe.cn/docs/api/id/177/aid/601或者http://apistore.baidu.com/apiworks/servicedetail/1116.html
- 在线解析网页信息,获取节假日情况:严重依赖被解析的网站网页,所以在选取网站的时候,要找稍微靠谱点的;
- 根据国家规定的法定节假日放假情况,每年录入系统,这种如果客户不怕麻烦的话。还是比较靠谱的;
本Demo将选择第二种来实现;
使用htmlunit在线解析网页信息,获取节假日情况
一开始是使用jsoup去解析网页的,效果不理想,如果网页是动态生成的时候,用jsoup遇到了各种问题,所以改成了htmlunit,总得来说htmlunit还是很强大的,能够模拟浏览器运行,被誉为java浏览器的开源实现;
首先去官网下载相关jar包,以及阅读相关文档:
http://htmlunit.sourceforge.net/
我这里解析的网页是360的万年历:
日历界面如下:
被解析的 HTML格式如下:
实现步骤:
1、加载页面;
2、循环等待页面加载完成(可能会有一些动态页面,是用javascript生成);
3、根据网页格式解析html内容,并提取关键信息存入封装好的对象;
注意点:
1、难点在于判断是否休假及假期类型,由于原页面并没有标明每一天的假期类型,所以这里的逻辑要自己去实现,详情参考代码;
2、之所以有个静态latestVocationName变量,是防止出现以下情况(出现该情况的概率极低;PS:方法要每天调用一次,该变量才生效):
代码实现:
定义一个中国日期类:
package com.pichen.tools.getDate; import java.util.Date; public class ChinaDate { /**
* 公历时间
*/
private Date solarDate; /**
* 农历日
*/
private String lunar; /**
* 公历日
*/
private String solar; /**
* 是否是 休
*/
private boolean isVacation = false;
/**
* 如果是 休情况下的假期名字
*/
private String VacationName = "非假期";
/**
* 是否是 班
*/
private boolean isWorkFlag = false; private boolean isSaturday = false;
private boolean isSunday = false;
/**
* @return the solarDate
*/
public Date getSolarDate() {
return solarDate;
}
/**
* @param solarDate the solarDate to set
*/
public void setSolarDate(Date solarDate) {
this.solarDate = solarDate;
}
/**
* @return the lunar
*/
public String getLunar() {
return lunar;
}
/**
* @param lunar the lunar to set
*/
public void setLunar(String lunar) {
this.lunar = lunar;
}
/**
* @return the solar
*/
public String getSolar() {
return solar;
}
/**
* @param solar the solar to set
*/
public void setSolar(String solar) {
this.solar = solar;
} /**
* @return the isVacation
*/
public boolean isVacation() {
return isVacation;
}
/**
* @param isVacation the isVacation to set
*/
public void setVacation(boolean isVacation) {
this.isVacation = isVacation;
}
/**
* @return the vacationName
*/
public String getVacationName() {
return VacationName;
}
/**
* @param vacationName the vacationName to set
*/
public void setVacationName(String vacationName) {
VacationName = vacationName;
}
/**
* @return the isWorkFlag
*/
public boolean isWorkFlag() {
return isWorkFlag;
}
/**
* @param isWorkFlag the isWorkFlag to set
*/
public void setWorkFlag(boolean isWorkFlag) {
this.isWorkFlag = isWorkFlag;
}
/**
* @return the isSaturday
*/
public boolean isSaturday() {
return isSaturday;
}
/**
* @param isSaturday the isSaturday to set
*/
public void setSaturday(boolean isSaturday) {
this.isSaturday = isSaturday;
}
/**
* @return the isSunday
*/
public boolean isSunday() {
return isSunday;
}
/**
* @param isSunday the isSunday to set
*/
public void setSunday(boolean isSunday) {
this.isSunday = isSunday;
} }
解析网页,并调用demo,打印本月详情,和当天详情:
package com.pichen.tools.getDate;
import java.io.IOException;
import java.net.MalformedURLException;
import java.text.DateFormat;
import java.text.ParseException;
import java.text.SimpleDateFormat;
import java.util.ArrayList;
import java.util.Date;
import java.util.List; import com.gargoylesoftware.htmlunit.FailingHttpStatusCodeException;
import com.gargoylesoftware.htmlunit.WebClient;
import com.gargoylesoftware.htmlunit.html.DomNodeList;
import com.gargoylesoftware.htmlunit.html.HtmlElement;
import com.gargoylesoftware.htmlunit.html.HtmlPage; public class Main { private static String latestVocationName=""; public String getVocationName(DomNodeList<HtmlElement> htmlElements, String date) throws ParseException{
String rst = ""; boolean pastTimeFlag = false;
DateFormat dateFormat = new SimpleDateFormat("yyyy/MM/dd");
Date paramDate = dateFormat.parse(date);
if(new Date().getTime() >= paramDate.getTime()){
pastTimeFlag = true;
} //first step //jugde if can get vocation name from html page
for(int i = 0; i < htmlElements.size(); i++){
HtmlElement element = htmlElements.get(i);
if(element.getAttribute("class").indexOf("vacation")!=-1){ boolean hitFlag = false;
String voationName = "";
for(; i < htmlElements.size(); i++){
HtmlElement elementTmp = htmlElements.get(i);
String liDate = elementTmp.getAttribute("date"); List<HtmlElement> lunar = elementTmp.getElementsByAttribute("span", "class", "lunar");
String lanarText = lunar.get(0).asText(); if(lanarText.equals("元旦")){
voationName = "元旦";
}else if(lanarText.equals("除夕")||lanarText.equals("春节")){
voationName = "春节";
}else if(lanarText.equals("清明")){
voationName = "清明";
}else if(lanarText.equals("国际劳动节")){
voationName = "国际劳动节";
}else if(lanarText.equals("端午节")){
voationName = "端午节";
}else if(lanarText.equals("中秋节")){
voationName = "中秋节";
}else if(lanarText.equals("国庆节")){
voationName = "国庆节";
} if(liDate.equals(date)){
hitFlag = true;
} if(elementTmp.getAttribute("class").indexOf("vacation")==-1){
break;
}
} if(hitFlag == true && !voationName.equals("")){
rst = voationName;
break;
} }else{
continue;
}
} //if first step fail(rarely), get from the latest Vocation name
if(rst.equals("")){
System.out.println("warning: fail to get vocation name from html page."); //you can judge by some simple rule //from the latest Vocation name
rst = Main.latestVocationName;
}else if(pastTimeFlag == true){
//更新《当前时间,且最近一次的可见的假期名
Main.latestVocationName = rst;
}
return rst;
} public List<ChinaDate> getCurrentDateInfo(){
WebClient webClient = null;
List<ChinaDate> dateList = null; try{
DateFormat dateFormat = new SimpleDateFormat("yyyy/MM/dd");
dateList = new ArrayList<ChinaDate>(); webClient = new WebClient();
HtmlPage page = webClient.getPage("http://hao.360.cn/rili/"); //最大等待60秒
for(int k = 0; k < 60; k++){
if(!page.getElementById("M-dates").asText().equals("")) break;
Thread.sleep(1000);
} //睡了8秒,等待页面加载完成...,有时候,页面可能获取不到,不稳定()
//Thread.sleep(8000); DomNodeList<HtmlElement> htmlElements = page.getElementById("M-dates").getElementsByTagName("li");
//System.out.println(htmlElements.size()); for(HtmlElement element : htmlElements){
ChinaDate chinaDate = new ChinaDate(); List<HtmlElement> lunar = element.getElementsByAttribute("span", "class", "lunar");
List<HtmlElement> solar = element.getElementsByAttribute("div", "class", "solar"); chinaDate.setLunar(lunar.get(0).asText());
chinaDate.setSolar(solar.get(0).asText());
chinaDate.setSolarDate(dateFormat.parse(element.getAttribute("date"))); if(element.getAttribute("class").indexOf("vacation")!=-1){
chinaDate.setVacation(true);
chinaDate.setVacationName(this.getVocationName(htmlElements, element.getAttribute("date"))); } if(element.getAttribute("class").indexOf("weekend")!=-1 &&
element.getAttribute("class").indexOf("last")==-1){
chinaDate.setSaturday(true);
}
if(element.getAttribute("class").indexOf("last weekend")!=-1){
chinaDate.setSunday(true);
}
if(element.getAttribute("class").indexOf("work")!=-1){
chinaDate.setWorkFlag(true);
}else if(chinaDate.isSaturday() == false &&
chinaDate.isSunday() == false &&
chinaDate.isVacation() == false ){
chinaDate.setWorkFlag(true);
}else{
chinaDate.setWorkFlag(false);
} dateList.add(chinaDate);
} }catch(Exception e){
e.printStackTrace();
System.out.println("get date from http://hao.360.cn/rili/ error~");
}finally{
webClient.close();
}
return dateList;
} public ChinaDate getTodayInfo(){
List<ChinaDate> dateList = this.getCurrentDateInfo();
DateFormat dateFormat = new SimpleDateFormat("yyyy/MM/dd");
for(ChinaDate date: dateList){
if(dateFormat.format(date.getSolarDate()).equals(dateFormat.format(new Date()))){
return date;
}
}
return new ChinaDate();
} public static void main(String[] args) throws FailingHttpStatusCodeException, MalformedURLException, IOException, InterruptedException { List<ChinaDate> dateList = new Main().getCurrentDateInfo();
ChinaDate today = new Main().getTodayInfo();
DateFormat dateFormat = new SimpleDateFormat("yyyy/MM/dd"); System.out.println("本月详情:");
for(ChinaDate date: dateList){
System.out.println(dateFormat.format(date.getSolarDate()) + " " + date.getVacationName());
} System.out.println("------------------------------------------------------------------------");
System.out.println("今日详情:");
System.out.println("日期:" + today.getSolarDate());
System.out.println("农历:"+today.getLunar());
System.out.println("公历:"+today.getSolar());
System.out.println("假期名:"+today.getVacationName());
System.out.println("是否周六:"+today.isSaturday());
System.out.println("是否周日:"+today.isSunday());
System.out.println("是否休假:"+today.isVacation());
System.out.println("是否工作日:"+today.isWorkFlag()); System.out.println("已发生的最近一次假期:" + Main.latestVocationName);
} }
运行程序,结果正确:
后续改进措施
当网页加载失败的时候,可以多次尝试;
可以考虑多找几个网站的日历进行解析,当其中一个抛出异常的时候,切换到另一个网站解析;
考虑增加邮件通知或短信通知功能,出现任何异常信息都能实时通知系统管理者;